Article ID Journal Published Year Pages File Type
6902213 Procedia Computer Science 2017 9 Pages PDF
Abstract
The focus of this research paper is to compare the different filter, wrapper and fuzzy rough set based feature selection methods based on three parameters namely execution time, number of features selected in the reduced subset and classifier accuracy. The results are analyzed using the different feature selection methods on cancer microarray gene expression datasets. This research work finds KNN classifier to produce higher classifier accuracy compared to traditional classifiers available in literature. Also fuzzy rough set based feature selection approach is computationally faster and produces lesser number of genes in the reduced subset compared to correlation based filter.
Related Topics
Physical Sciences and Engineering Computer Science Computer Science (General)
Authors
, , ,